© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 7558
    Prev
    Next
    INDEX
    Explanations

    references to specific named entities or labels, particularly organization or location names

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Yam
    -0.82
    Geplaatst
    -0.81
    +/**
    -0.72
     Compagn
    -0.71
     Zink
    -0.69
     GenerationType
    -0.68
     Kea
    -0.66
     Nore
    -0.66
    DockStyle
    -0.65
    RadioGroup
    -0.65
    POSITIVE LOGITS
     Pooh
    0.83
     Brito
    0.76
    UMBIA
    0.69
     Bee
    0.68
     Esposito
    0.68
     Potter
    0.67
     Harry
    0.66
     Beatrix
    0.65
    Bees
    0.65
     osteo
    0.64
    Activations Density 1.407%

    No Known Activations